kernel-ui
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to review and implement UI components based on user-provided code or design specifications, creating a potential attack surface if the input contains malicious instructions.
- Ingestion points: The agent processes UI components, pages, or screens for review and implementation as defined in the
whentriggers inSKILL.md. - Boundary markers: Absent. There are no explicit instructions to the agent to distinguish between design data and potential natural language instructions embedded in code comments or strings.
- Capability inventory: The skill's primary capabilities are limited to generating UI code and providing text-based audits. It does not perform network operations, file system modifications, or command execution.
- Sanitization: Absent. The skill does not prescribe specific methods for sanitizing user-provided UI code before processing.
Audit Metadata